Professional Documents
Culture Documents
VM The Best Method PDF
VM The Best Method PDF
VM The Best Method PDF
OF RESEARCH RESULTS
Veljko Milutinovic
emilutiv@etf.bg.ac.yu
(381-11) 762-214
This title is didactic since it is immediately obvious 3. Structure of the Figures and/or Tables
that the main idea is to apply the entry consistency and the Related Captions
model to temporal data and the lazy release consistency
Figures and tables should include only language-
model to spatial data, for the performance which is better
independent mnemonics (derived from English
than applying only one of the two models to all data.
language), which is especially important for non-
This title is also lapidaric, since one immediately
English-speaking researchers, and for those writing for
starts thinking about how the selective application of two
many languages, so it is easier to switch back and forth
different consistency models was really implemented.
between languages.
An alternative (bad) title would be:
All details must be clearly visible, even after the same
SOME ISSUES figure is ported to a transparency for an oral
IN MEMORY CONSISTENCY MODELING presentation.
Captions deserve a special attention, which is
People would tend to stay away from a paper with neglected in a typical written presentation. The main
such a title, since that kind of title might be viewed as an issue is that reading only the figure captions of the paper
introduction into a contents-free paper, unless it comes can substitute the first rough reading of the entire paper.
form a well known expert who has a reputation of This goal is achieved more successfully if the caption
knowing what he/she is doing. Consequently, a good includes the following five elements:
idea may not be noticed by the research community, and
those who reinvent it at a later time will get the credit (a) Title with the main highlight, i.e. the main
instead of the initial inventor. issue to be demonstrated by the corresponding
figure/table;
(b) Legend, to explain all language-independent
6WUXFWXUHRIWKH$EVWUDFW
mnemonics inside the figure/table;
Wherever possible, the abstract of a research paper (c) Description, of one or more phenomena which
should include the following five elements: deserve attention (e.g., curves A and B cross
(a) Problem statement of the research under each other at X=16);
consideration; (d) Explanation, of the essential reason for such a
(b) A short list of existing solutions and what is behavior (e.g., the curves cross each other
their drawback, from the point of view of the because for higher values of X, the following
above defined problem statement; happens ...);
(c) Essence of the proposed solution, and why it is (e) Implication, or what is to be kept in mind when
expected to be better under the same conditions; designing/engineering a system to exploit the
(d) What type of analysis was done to show that the above noticed phenomenon (e.g., increasing the
proposed solution is really better than any of the size of register file helps until the number of
existing ones, from both the performance and registers reaches a critical value; after that ...).